Face Generation

In this project, you'll use generative adversarial networks to generate new images of faces.

Get the Data

You'll be using two datasets in this project:

  • MNIST
  • CelebA

Since the celebA dataset is complex and you're doing GANs in a project for the first time, we want you to test your neural network on MNIST before CelebA. Running the GANs on MNIST will allow you to see how well your model trains sooner.

If you're using FloydHub, set data_dir to "/input" and use the FloydHub data ID "R5KrjnANiKVhLWAkpXhNBe".

In [1]:
data_dir = './data'

# FloydHub - Use with data ID "R5KrjnANiKVhLWAkpXhNBe"
#data_dir = '/input'


"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper

helper.download_extract('mnist', data_dir)
helper.download_extract('celeba', data_dir)
Found mnist Data
Found celeba Data

Explore the Data

MNIST

As you're aware, the MNIST dataset contains images of handwritten digits. You can view the first number of examples by changing show_n_images.

In [2]:
show_n_images = 25

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
%matplotlib inline
import os
from glob import glob
from matplotlib import pyplot

mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'mnist/*.jpg'))[:show_n_images], 28, 28, 'L')
pyplot.imshow(helper.images_square_grid(mnist_images, 'L'), cmap='gray')
Out[2]:
<matplotlib.image.AxesImage at 0x7f84c2a72470>

CelebA

The CelebFaces Attributes Dataset (CelebA) dataset contains over 200,000 celebrity images with annotations. Since you're going to be generating faces, you won't need the annotations. You can view the first number of examples by changing show_n_images.

In [3]:
show_n_images = 25

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'img_align_celeba/*.jpg'))[:show_n_images], 28, 28, 'RGB')
pyplot.imshow(helper.images_square_grid(mnist_images, 'RGB'))
Out[3]:
<matplotlib.image.AxesImage at 0x7f84bf883a20>

Preprocess the Data

Since the project's main focus is on building the GANs, we'll preprocess the data for you. The values of the MNIST and CelebA dataset will be in the range of -0.5 to 0.5 of 28x28 dimensional images. The CelebA images will be cropped to remove parts of the image that don't include a face, then resized down to 28x28.

The MNIST images are black and white images with a single color channel while the CelebA images have 3 color channels (RGB color channel).

Build the Neural Network

You'll build the components necessary to build a GANs by implementing the following functions below:

  • model_inputs
  • discriminator
  • generator
  • model_loss
  • model_opt
  • train

Check the Version of TensorFlow and Access to GPU

This will check to make sure you have the correct version of TensorFlow and access to a GPU

In [4]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from distutils.version import LooseVersion
import warnings
import tensorflow as tf

# Check TensorFlow Version
assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer.  You are using {}'.format(tf.__version__)
print('TensorFlow Version: {}'.format(tf.__version__))

# Check for a GPU
if not tf.test.gpu_device_name():
    warnings.warn('No GPU found. Please use a GPU to train your neural network.')
else:
    print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))
TensorFlow Version: 1.1.0
Default GPU Device: /gpu:0

Input

Implement the model_inputs function to create TF Placeholders for the Neural Network. It should create the following placeholders:

  • Real input images placeholder with rank 4 using image_width, image_height, and image_channels.
  • Z input placeholder with rank 2 using z_dim.
  • Learning rate placeholder with rank 0.

Return the placeholders in the following the tuple (tensor of real input images, tensor of z data)

In [5]:
import problem_unittests as tests

def model_inputs(image_width, image_height, image_channels, z_dim):
    """
    Create the model inputs
    :param image_width: The input image width
    :param image_height: The input image height
    :param image_channels: The number of image channels
    :param z_dim: The dimension of Z
    :return: Tuple of (tensor of real input images, tensor of z data, learning rate)
    """
    # TODO: Implement Function
    
    #HWC
    input_real = tf.placeholder(tf.float32, [None, image_height, image_width, image_channels], name='input_real')
    input_z = tf.placeholder(tf.float32, [None, z_dim], name='input_z')
    learning_rate = tf.placeholder(tf.float32, name='learning_rate')
    
    return (input_real, input_z, learning_rate)


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_inputs(model_inputs)
Tests Passed

Discriminator

Implement discriminator to create a discriminator neural network that discriminates on images. This function should be able to reuse the variabes in the neural network. Use tf.variable_scope with a scope name of "discriminator" to allow the variables to be reused. The function should return a tuple of (tensor output of the generator, tensor logits of the generator).

In [6]:
# Shape during CNN: 28x28xCH (3 or 1) -> 14x14x64 -> 7x7x128 -> 4x4x256 -> 1 

def discriminator(images, reuse=False):
    """
    Create the discriminator network
    :param image: Tensor of input image(s)
    :param reuse: Boolean if the weights should be reused
    :return: Tuple of (tensor output of the discriminator, tensor logits of the discriminator)
    """
    
    alpha = 0.2
    keep_prob = 0.7
    
    # TODO: Implement Function
    with tf.variable_scope('discriminator', reuse=reuse):
    
        # Input layer is 28x28xCH (3 or 1) -> 14x14x64
        x = tf.layers.conv2d(inputs=images, filters=64, kernel_size=(3,3), strides=2, activation=None,
                             padding='same', kernel_initializer=tf.contrib.layers.xavier_initializer())
        # No batch normalization, better results
        x = tf.maximum(alpha * x, x)
        x = tf.nn.dropout(x, keep_prob=keep_prob)
        
        # -> 7x7x128
        x1 = tf.layers.conv2d(x, filters = 128, kernel_size=(3,3), strides=2, activation=None,
                              padding='same', kernel_initializer=tf.contrib.layers.xavier_initializer())
        x1 = tf.layers.batch_normalization(x1, training=True)
        x1 = tf.maximum(alpha * x1, x1)
        x1 = tf.nn.dropout(x1, keep_prob=keep_prob)
        
        # -> 4x4x256
        x2 = tf.layers.conv2d(x1, filters=256, kernel_size=(3,3), strides=2, activation=None,
                              padding='same', kernel_initializer=tf.contrib.layers.xavier_initializer())
        x2 = tf.layers.batch_normalization(x2, training=True)
        x2 = tf.maximum(alpha * x2, x2)
        x2 = tf.nn.dropout(x2, keep_prob=keep_prob)
        
        # Reshape for final dense layer -> units = 1 for sigmoid
        x3 = tf.reshape(x2, shape=(-1, 4*4*256))
        logits = tf.layers.dense(inputs=x3, units=1)
        
        out = tf.sigmoid(logits)
    
    return (out, logits)


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_discriminator(discriminator, tf)
Tests Passed

Generator

Implement generator to generate an image using z. This function should be able to reuse the variabes in the neural network. Use tf.variable_scope with a scope name of "generator" to allow the variables to be reused. The function should return the generated 28 x 28 x out_channel_dim images.

In [7]:
# Shape during CNN: 100 (z_dim) -> 4x4x512 -> 7x7x256 -> 14x14x128 -> 28x28xCH

def generator(z, out_channel_dim, is_train=True):
    """
    Create the generator network
    :param z: Input z
    :param out_channel_dim: The number of channels in the output image
    :param is_train: Boolean if generator is being used for training
    :return: The tensor output of the generator
    """
    
    alpha = 0.2
    keep_prob = 0.7
    
    with tf.variable_scope('generator', reuse = not is_train):

        #1st block -> 4x4x512
        # First fully connected layer
        # From input (1D to 1D of 4*4*512)
        x = tf.layers.dense(z, units=(4*4*512))
        # Reshahe the fully connected result (HWC)
        x1 = tf.reshape(x, shape=(-1,4,4,512))
        # Batch Norm + Leaky ReLU
        x1 = tf.layers.batch_normalization(x1, training=is_train)
        x1 = tf.maximum(alpha * x1, x1)
        x1 = tf.nn.dropout(x1, keep_prob=keep_prob)
        
        #2nd block -> 8x8x256
        # Strides 2 with padding 'same' give the output 8x8 (for the filters we explicitly set 256)
        x2 = tf.layers.conv2d_transpose(x1, filters=256, kernel_size=(3,3), strides=2,
                                        padding='same', activation=None,
                                        kernel_initializer=tf.contrib.layers.xavier_initializer())
        # Batch Norm + Leaky ReLU
        x2 = tf.layers.batch_normalization(x2, training=is_train)
        x2 = tf.maximum(alpha * x2, x2)
        x2 = tf.nn.dropout(x2, keep_prob=keep_prob)
        # Resize to 7x7x256
        x2 = tf.image.resize_nearest_neighbor(images=x2, size=(7, 7))
        
        #3rd block -> 14x14x128
        # Strides 2 with padding 'same' give the output 14x14 (for the filters we explicitly set 128)
        x3 = tf.layers.conv2d_transpose(x2, filters=128, kernel_size=(3,3), strides=2, 
                                        padding='same', activation=None,
                                        kernel_initializer=tf.contrib.layers.xavier_initializer())
        x3 = tf.layers.batch_normalization(x3, training=is_train)
        x3 = tf.maximum(alpha * x3, x3)
        x3 = tf.nn.dropout(x3, keep_prob=keep_prob)
        
        #4th block -> 28x28xCH (no batch normalization and use tanh activation)
        logits = tf.layers.conv2d_transpose(x3, filters=out_channel_dim, kernel_size=(3,3), strides=2,
                                        padding='same', activation=None,
                                        kernel_initializer=tf.contrib.layers.xavier_initializer())
        
        # Output layer, 28x28xCH
        out = tf.tanh(logits)
    
    return out


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(generator, tf)
Tests Passed

Loss

Implement model_loss to build the GANs for training and calculate the loss. The function should return a tuple of (discriminator loss, generator loss). Use the following functions you implemented:

  • discriminator(images, reuse=False)
  • generator(z, out_channel_dim, is_train=True)
In [8]:
def model_loss(input_real, input_z, out_channel_dim):
    """
    Get the loss for the discriminator and generator
    :param input_real: Images from the real dataset
    :param input_z: Z input
    :param out_channel_dim: The number of channels in the output image
    :return: A tuple of (discriminator loss, generator loss)
    """
    # TODO: Implement Function
    g_out = generator(z=input_z, out_channel_dim=out_channel_dim, is_train=True)
    d_out_real, d_logits_real = discriminator(images=input_real, reuse=False)
    d_out_fake, d_logits_fake = discriminator(images=g_out, reuse=True)
    
    d_loss_real = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real,
                                                                         labels=tf.ones_like(d_logits_real)))
    d_loss_fake = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake,
                                                                        labels=tf.zeros_like(d_logits_fake)))
    
    g_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake,
                                                                   labels=tf.ones_like(d_logits_fake)))
    
    d_loss = d_loss_real + d_loss_fake
    
    return (d_loss, g_loss)


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_loss(model_loss)
Tests Passed

Optimization

Implement model_opt to create the optimization operations for the GANs. Use tf.trainable_variables to get all the trainable variables. Filter the variables with names that are in the discriminator and generator scope names. The function should return a tuple of (discriminator training operation, generator training operation).

In [9]:
def model_opt(d_loss, g_loss, learning_rate, beta1):
    """
    Get optimization operations
    :param d_loss: Discriminator loss Tensor
    :param g_loss: Generator loss Tensor
    :param learning_rate: Learning Rate Placeholder
    :param beta1: The exponential decay rate for the 1st moment in the optimizer
    :return: A tuple of (discriminator training operation, generator training operation)
    """
    # TODO: Implement Function
    
    t_vars = tf.trainable_variables()
    d_vars = [var for var in t_vars if var.name.startswith('discriminator')]
    g_vars = [var for var in t_vars if var.name.startswith('generator')]
    
    with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
        d_opt = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=beta1).minimize(d_loss, var_list=d_vars)
        g_opt = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=beta1).minimize(g_loss, var_list=g_vars)
    
    return (d_opt, g_opt)


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_opt(model_opt, tf)
Tests Passed

Neural Network Training

Show Output

Use this function to show the current output of the generator during training. It will help you determine how well the GANs is training.

In [10]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np

def show_generator_output(sess, n_images, input_z, out_channel_dim, image_mode):
    """
    Show example output for the generator
    :param sess: TensorFlow session
    :param n_images: Number of Images to display
    :param input_z: Input Z Tensor
    :param out_channel_dim: The number of channels in the output image
    :param image_mode: The mode to use for images ("RGB" or "L")
    """
    cmap = None if image_mode == 'RGB' else 'gray'
    z_dim = input_z.get_shape().as_list()[-1]
    example_z = np.random.uniform(-1, 1, size=[n_images, z_dim])

    samples = sess.run(
        generator(input_z, out_channel_dim, False),
        feed_dict={input_z: example_z})

    images_grid = helper.images_square_grid(samples, image_mode)
    pyplot.imshow(images_grid, cmap=cmap)
    pyplot.show()

Train

Implement train to build and train the GANs. Use the following functions you implemented:

  • model_inputs(image_width, image_height, image_channels, z_dim)
  • model_loss(input_real, input_z, out_channel_dim)
  • model_opt(d_loss, g_loss, learning_rate, beta1)

Use the show_generator_output to show generator output while you train. Running show_generator_output for every batch will drastically increase training time and increase the size of the notebook. It's recommended to print the generator output every 100 batches.

In [11]:
def train(epoch_count, batch_size, z_dim, learning_rate, beta1, get_batches, data_shape, data_image_mode):
    """
    Train the GAN
    :param epoch_count: Number of epochs
    :param batch_size: Batch Size
    :param z_dim: Z dimension
    :param learning_rate: Learning Rate
    :param beta1: The exponential decay rate for the 1st moment in the optimizer
    :param get_batches: Function to get batches
    :param data_shape: Shape of the data (batch, h, w, c)
    :param data_image_mode: The image mode to use for images ("RGB" or "L")
    """
    # Build Model
    height = data_shape[1]
    width = data_shape[2]
    channels = data_shape[3]
    
    #Get input placeholders
    input_real, input_z, learning_rate_p = model_inputs(width, height, channels, z_dim)
    # Get losses
    d_loss, g_loss = model_loss(input_real, input_z, channels)
    # Get optimizer
    d_opt, g_opt = model_opt(d_loss, g_loss, learning_rate_p, beta1)
    
    # Prepare the shape of z input for testing during training (zero filled tensor of the correct shape)
    test_images = 16
    test_z_shape = tf.zeros((test_images, z_dim))
    
    print_batch_step = 100
    
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for epoch_i in range(epoch_count):
            
            batch_index = 0
            
            for batch_images in get_batches(batch_size):
                # TODO: Train Model

                # real images are in range [-0.5, 0.5], while generated are in range [-1.0, 1.0]
                batch_images = batch_images * 2
                
                # Initialize a input z for the batch
                batch_z = np.random.uniform(-1, 1, size=(batch_size, z_dim))
                
                # Run optimizers
                _ = sess.run(d_opt, feed_dict={input_real: batch_images, input_z: batch_z,
                                               learning_rate_p: learning_rate})
                _ = sess.run(g_opt, feed_dict={input_z: batch_z, input_real: batch_images,
                                               learning_rate_p: learning_rate})
                
                # Print losses
                if batch_index % print_batch_step == 0:
                    train_loss_d = d_loss.eval({input_z: batch_z, input_real: batch_images})
                    train_loss_g = g_loss.eval({input_z: batch_z})

                    print("\nEpoch {}/{}...".format(epoch_i + 1, epoch_count),
                          "Discriminator Loss: {:.4f}...".format(train_loss_d),
                          "Generator Loss: {:.4f}".format(train_loss_g))
                
                if batch_index % print_batch_step == 0:
                    # Here test_z_shape is used only to retrieve the shape, the function initialize
                    # another random z to test the generator
                    show_generator_output(sess, test_images, test_z_shape, channels, data_image_mode)
                
                batch_index += 1

            
                
                

MNIST

Test your GANs architecture on MNIST. After 2 epochs, the GANs should be able to generate images that look like handwritten digits. Make sure the loss of the generator is lower than the loss of the discriminator or close to 0.

In [12]:
batch_size = 64
z_dim = 100
learning_rate = 0.0002
beta1 = 0.5


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 2

mnist_dataset = helper.Dataset('mnist', glob(os.path.join(data_dir, 'mnist/*.jpg')))
with tf.Graph().as_default():
    train(epochs, batch_size, z_dim, learning_rate, beta1, mnist_dataset.get_batches,
          mnist_dataset.shape, mnist_dataset.image_mode)
Epoch 1/2... Discriminator Loss: 1.4300... Generator Loss: 0.9442
Epoch 1/2... Discriminator Loss: 0.5391... Generator Loss: 2.4576
Epoch 1/2... Discriminator Loss: 0.4957... Generator Loss: 3.1078
Epoch 1/2... Discriminator Loss: 0.7046... Generator Loss: 1.3171
Epoch 1/2... Discriminator Loss: 0.7136... Generator Loss: 1.8548
Epoch 1/2... Discriminator Loss: 0.8141... Generator Loss: 1.6883
Epoch 1/2... Discriminator Loss: 1.0441... Generator Loss: 1.5399
Epoch 1/2... Discriminator Loss: 0.9161... Generator Loss: 1.2009
Epoch 1/2... Discriminator Loss: 0.8567... Generator Loss: 1.8115
Epoch 1/2... Discriminator Loss: 0.7583... Generator Loss: 1.4179
Epoch 2/2... Discriminator Loss: 1.0651... Generator Loss: 0.8530
Epoch 2/2... Discriminator Loss: 0.8591... Generator Loss: 2.6464
Epoch 2/2... Discriminator Loss: 0.8171... Generator Loss: 1.9289
Epoch 2/2... Discriminator Loss: 1.0703... Generator Loss: 1.3734
Epoch 2/2... Discriminator Loss: 0.9713... Generator Loss: 2.1519
Epoch 2/2... Discriminator Loss: 0.9524... Generator Loss: 2.0736
Epoch 2/2... Discriminator Loss: 0.9426... Generator Loss: 1.3058
Epoch 2/2... Discriminator Loss: 0.9781... Generator Loss: 1.5611
Epoch 2/2... Discriminator Loss: 0.9608... Generator Loss: 2.0618
Epoch 2/2... Discriminator Loss: 0.9679... Generator Loss: 2.1987

CelebA

Run your GANs on CelebA. It will take around 20 minutes on the average GPU to run one epoch. You can run the whole epoch or stop when it starts to generate realistic faces.

In [13]:
batch_size = 32
z_dim = 100
learning_rate = 0.0002
beta1 = 0.5


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 1

celeba_dataset = helper.Dataset('celeba', glob(os.path.join(data_dir, 'img_align_celeba/*.jpg')))
with tf.Graph().as_default():
    train(epochs, batch_size, z_dim, learning_rate, beta1, celeba_dataset.get_batches,
          celeba_dataset.shape, celeba_dataset.image_mode)
Epoch 1/1... Discriminator Loss: 1.4992... Generator Loss: 0.5704
Epoch 1/1... Discriminator Loss: 0.1847... Generator Loss: 2.8850
Epoch 1/1... Discriminator Loss: 0.2858... Generator Loss: 2.4452
Epoch 1/1... Discriminator Loss: 0.2290... Generator Loss: 3.3912
Epoch 1/1... Discriminator Loss: 0.9874... Generator Loss: 1.6273
Epoch 1/1... Discriminator Loss: 0.3390... Generator Loss: 3.3908
Epoch 1/1... Discriminator Loss: 0.5500... Generator Loss: 2.7708
Epoch 1/1... Discriminator Loss: 1.1523... Generator Loss: 1.2102
Epoch 1/1... Discriminator Loss: 0.7740... Generator Loss: 2.3064
Epoch 1/1... Discriminator Loss: 0.6564... Generator Loss: 2.1519
Epoch 1/1... Discriminator Loss: 0.8929... Generator Loss: 1.4832
Epoch 1/1... Discriminator Loss: 0.8336... Generator Loss: 1.7716
Epoch 1/1... Discriminator Loss: 1.0207... Generator Loss: 1.9995
Epoch 1/1... Discriminator Loss: 0.9782... Generator Loss: 1.0522
Epoch 1/1... Discriminator Loss: 0.6210... Generator Loss: 1.8436
Epoch 1/1... Discriminator Loss: 0.7982... Generator Loss: 1.5393
Epoch 1/1... Discriminator Loss: 0.7648... Generator Loss: 2.1181
Epoch 1/1... Discriminator Loss: 0.6301... Generator Loss: 1.8636
Epoch 1/1... Discriminator Loss: 0.6663... Generator Loss: 1.3128
Epoch 1/1... Discriminator Loss: 0.6479... Generator Loss: 1.4847
Epoch 1/1... Discriminator Loss: 1.1120... Generator Loss: 1.3081
Epoch 1/1... Discriminator Loss: 1.1187... Generator Loss: 0.8853
Epoch 1/1... Discriminator Loss: 1.3307... Generator Loss: 1.5806
Epoch 1/1... Discriminator Loss: 1.0505... Generator Loss: 2.0913
Epoch 1/1... Discriminator Loss: 0.8309... Generator Loss: 1.4655
Epoch 1/1... Discriminator Loss: 1.1522... Generator Loss: 1.0228
Epoch 1/1... Discriminator Loss: 1.0249... Generator Loss: 1.4104
Epoch 1/1... Discriminator Loss: 0.7783... Generator Loss: 1.3375
Epoch 1/1... Discriminator Loss: 0.9882... Generator Loss: 1.4455
Epoch 1/1... Discriminator Loss: 0.8207... Generator Loss: 1.6732
Epoch 1/1... Discriminator Loss: 0.9292... Generator Loss: 1.1466
Epoch 1/1... Discriminator Loss: 0.9592... Generator Loss: 1.0320
Epoch 1/1... Discriminator Loss: 0.9132... Generator Loss: 1.8459
Epoch 1/1... Discriminator Loss: 0.8080... Generator Loss: 1.7968
Epoch 1/1... Discriminator Loss: 1.0428... Generator Loss: 0.8994
Epoch 1/1... Discriminator Loss: 1.0195... Generator Loss: 1.3712
Epoch 1/1... Discriminator Loss: 1.0708... Generator Loss: 1.1637
Epoch 1/1... Discriminator Loss: 0.9060... Generator Loss: 0.9366
Epoch 1/1... Discriminator Loss: 0.7594... Generator Loss: 1.7466
Epoch 1/1... Discriminator Loss: 1.0231... Generator Loss: 1.3857
Epoch 1/1... Discriminator Loss: 0.7265... Generator Loss: 2.1902
Epoch 1/1... Discriminator Loss: 0.7252... Generator Loss: 1.4280
Epoch 1/1... Discriminator Loss: 0.8158... Generator Loss: 1.1125
Epoch 1/1... Discriminator Loss: 0.9178... Generator Loss: 1.5658
Epoch 1/1... Discriminator Loss: 1.0037... Generator Loss: 1.6083
Epoch 1/1... Discriminator Loss: 0.9420... Generator Loss: 0.9717
Epoch 1/1... Discriminator Loss: 0.7106... Generator Loss: 1.4100
Epoch 1/1... Discriminator Loss: 0.9220... Generator Loss: 1.4756
Epoch 1/1... Discriminator Loss: 0.7632... Generator Loss: 1.2521
Epoch 1/1... Discriminator Loss: 0.5968... Generator Loss: 2.4771
Epoch 1/1... Discriminator Loss: 0.7814... Generator Loss: 1.8612
Epoch 1/1... Discriminator Loss: 0.5707... Generator Loss: 1.9910
Epoch 1/1... Discriminator Loss: 0.7753... Generator Loss: 1.4330
Epoch 1/1... Discriminator Loss: 0.7314... Generator Loss: 1.6247
Epoch 1/1... Discriminator Loss: 0.7590... Generator Loss: 1.7867
Epoch 1/1... Discriminator Loss: 0.7373... Generator Loss: 1.9561
Epoch 1/1... Discriminator Loss: 1.1374... Generator Loss: 1.5037
Epoch 1/1... Discriminator Loss: 0.7175... Generator Loss: 1.9867
Epoch 1/1... Discriminator Loss: 0.9059... Generator Loss: 1.3332
Epoch 1/1... Discriminator Loss: 0.6721... Generator Loss: 1.6952
Epoch 1/1... Discriminator Loss: 1.0419... Generator Loss: 1.0435
Epoch 1/1... Discriminator Loss: 0.6480... Generator Loss: 2.0180
Epoch 1/1... Discriminator Loss: 0.9345... Generator Loss: 1.3192
Epoch 1/1... Discriminator Loss: 0.6667... Generator Loss: 2.0065

Submitting This Project

When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as "dlnd_face_generation.ipynb" and save it as a HTML file under "File" -> "Download as". Include the "helper.py" and "problem_unittests.py" files in your submission.